Information Retrieval

Artificial Intelligence 16 Sep 2026 6 min read

Preserve Token-Level Signals with Late Interaction Retrieval

A single embedding compresses an entire query or document into one vector before similarity is computed. That representation is convenient for approximate nearest-neighbor search, but every token-level signal must survive the compression step. Late interaction retrieval keeps the independent encoding property while postponing part of the query-document comparison until search time. The core change is representational. Instead of storing one vector per document, a late interaction model can retain a set of contextual token vectors. A query is also represented by multiple vectors. Relevance is then computed from interactions between those two sets rather than from one global dot product.

Artificial Intelligence Embeddings

Artificial Intelligence 11 Sep 2026 10 min read

Fuse Keyword and Vector Search with Reciprocal Rank Fusion

Fuse Keyword and Vector Search with Reciprocal Rank Fusion A RAG system often needs two kinds of retrieval at once. Keyword search is good at exact strings such as product codes, error messages, and names. Vector search can recover passages that express the same idea with different words. Running both is easy; combining their scores correctly is where many implementations become fragile. Reciprocal rank fusion (RRF) solves that problem by ignoring raw scores and combining rank positions instead. BM25 and vector similarity do not share a stable numeric scale. The sections below calculate RRF on a small example, then cover the parameters and evaluation checks that matter in hybrid retrieval.

Artificial Intelligence RAG

Artificial Intelligence 09 Sep 2026 11 min read

Diversify RAG Retrieval with Maximum Marginal Relevance

A retrieval-augmented generation (RAG) system can retrieve highly relevant chunks and still build a poor context. The problem is redundancy. Imagine a support assistant answering a question about an API timeout. Vector search returns five chunks, but four are slightly different copies of the same timeout definition. The fifth useful chunk about retry behavior never reaches the model. Each result looked relevant in isolation, yet the set wastes most of its context budget repeating one idea.

Artificial Intelligence RAG